© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 16396
    Prev
    Next
    INDEX
    Explanations

    names of people or characters followed by an indication of significance or action

    oai_token-act-pair · gpt-3.5-turbo

    the character 'Ļ' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disadvant
    -0.91
     constitu
    -0.91
     mathemat
    -0.91
     vulner
    -0.83
     princ
    -0.81
     contrace
    -0.80
     regul
    -0.78
     therap
    -0.78
     comprom
    -0.77
    raints
    -0.77
    POSITIVE LOGITS
    ï¸ı
    1.15
    İ
    1.01
    ï¸
    0.93
    IJ
    0.88
    à¥
    0.87
    Ĩ
    0.87
    Ķ
    0.83
    ı
    0.83
    ĩ
    0.82
    Ļ
    0.81
    Activations Density 0.346%

    No Known Activations